USA’s Battle with COVID-19
rm(list=ls())
source("../DATA/movavg.R")
db <- dbConnect(SQLite(), dbname="../COVID-19-DB/OURWORLD.sqlite3")
df <- dbGetQuery(db,"select * from JHU")
df <- subset(df,location =="United States" )
df$date <- as.Date(df$date)
sum(df$new_cases,na.rm = TRUE)
## [1] 26435556
sum(df$new_deaths,na.rm=TRUE)
## [1] 446885
US <- subset(df,date >="2020-04-01" & new_cases >=1)
US <- US[order(US$date,decreasing = TRUE),]
US$MAC <- ma(US$new_cases,7,centre=TRUE)
US$MAD <- ma(US$new_deaths,7,centre=TRUE)
US$Rate <- US$new_deaths/US$new_cases
USA’s Vaccine Rollout
vac <- dbGetQuery(db,"select * from OWID where location = 'United States'")
vac$date <- as.Date(vac$date)
vac <- vac[order(vac$date),]
vac <- vac %>% filter(date >="2012-1-15")
vac <- vac %>%select(date,location,iso_code,new_vaccinations,
total_vaccinations,population,
people_vaccinated,people_fully_vaccinated
) %>%
na.omit()
summary(vac$speople_vaccinated)
## Length Class Mode
## 0 NULL NULL
summary(vac$people_fully_vaccinated)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1342086 2666455 3414156 3693339 4900589 6064792
Doses Administered
p5 <- ggplot(vac) + geom_line(aes(x=date,y=new_vaccinations)) +
scale_y_continuous(labels=comma) +
labs(title="USA's Daily Doses By Date") +
geom_point(aes(x=date,y=new_vaccinations))
ggplotly(p5)
p6 <- ggplot(vac) + geom_line(aes(x=date,y=total_vaccinations)) +
scale_y_continuous(labels=comma) +
labs(title="USA's Total (Full) Doses Date")
ggplotly(p6)
People Vaccinated
p5 <- ggplot(vac) + geom_line(aes(x=date,y=people_vaccinated)) +
scale_y_continuous(labels=comma) +
labs(title="USA's Number of People Vaccinatations By Date")
# geom_smooth(aes(x=date,y=))
ggplotly(p5)
p6 <- ggplot(vac) + geom_line(aes(x=date,y=people_fully_vaccinated)) +
scale_y_continuous(labels=comma) +
labs(title="USA's Total Number of People Fully Vaccinated By Date")
ggplotly(p6)
vac$Rate <- vac$people_vaccinated/vac$population
vac$Rate1 <- vac$people_fully_vaccinated/vac$population
p7 <- ggplot(vac) + geom_line(aes(x=date,y=Rate,col="Total People")) +
geom_line(aes(x=date,y=Rate1,col="Full Vaccine")) +
scale_y_continuous(labels=percent) + ylim(0,0.15) +
labs(title="USA's vaccination Rate By Day")
## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.
ggplotly(p7)
USA COVID19 Mortality Rate
A <- subset(US,date >="2020-02-01")
ggplot(A) + # geom_line(aes(x=date,y=Rate)) +
scale_y_continuous(labels = scales::percent) +
labs(title="USA COVID19 Mortality Rate ",x="Date date",y="Mortality Rate") +
geom_hline(yintercept = mean(A$Rate),col="red") +
geom_line(aes(x=date,y=Rate,col="Rolling Mean")) +
geom_smooth(aes(x=date,y=Rate))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
Plot of Daily Cases and Deaths
daily_new_cases <-ggplot(US) +
labs(title="COVID-19 new_cases by Date",y="Cases") +
geom_line(aes(x=date,y=MAC,col="Mov Average")) +
geom_line(aes(x=date,y=new_cases,col="Daily Cases"))
ggplotly(daily_new_cases)
## Don't know how to automatically pick scale for object of type ts. Defaulting to continuous.
daily_new_deaths <-ggplot(US) +
labs(title="COVID-19 Deaths by Date",col="Deaths",y="Deaths") +
geom_line(aes(x=date,y=MAD,col="Mov. Average")) +
geom_line(aes(x=date,y=new_deaths,col="Daily Deaths"))
ggplotly(daily_new_deaths)
## Don't know how to automatically pick scale for object of type ts. Defaulting to continuous.
Non-Moving Average By Week and By Month
US$Monthly <- as.Date(cut(US$date,
breaks = "month"))
US$Weekly <- as.Date(cut(US$date,
breaks = "week",
start.on.monday = FALSE))
Weekly_new_cases <- aggregate(new_cases~Weekly,US,FUN=sum)
Weekly_new_deaths <- aggregate(new_deaths~Weekly,US,FUN=sum)
Weekly_new_cases$DRate <- Weekly_new_deaths$new_deaths/Weekly_new_cases$new_cases
Weekly_new_cases$LivedSaved <- Weekly_new_cases$new_cases * (max(Weekly_new_cases$DRate) - Weekly_new_cases$DRate)
ggplot(Weekly_new_cases) + geom_col(aes(x=Weekly,y=new_cases)) +
labs(title="Weekly new_cases",x="Date date", y="Weekly new_cases") +
scale_alpha_date()
ggplot(Weekly_new_deaths) + geom_col(aes(x=Weekly,y=new_deaths)) +
labs(title="Weekly new_deaths",x="Date date", y="Weekly new_deaths")
Monthly new_cases and new_deaths
Monthly_new_cases <- aggregate(new_cases~Monthly,US,FUN=sum)
Monthly_new_deaths <- aggregate(new_deaths~Monthly,US,FUN=sum)
Monthly_new_cases$DRate <- Monthly_new_deaths$new_deaths/Monthly_new_cases$new_cases
Monthly_new_cases$LivedSaved <- Monthly_new_cases$new_cases * (max(Monthly_new_cases$DRate) - Monthly_new_cases$DRate) * 100
ggplot(Monthly_new_cases) + geom_col(aes(x=Monthly,y=new_cases)) +
labs(title="Monthly new_cases") +
scale_y_continuous(labels=scales::comma) +
scale_alpha_date()
ggplot(Monthly_new_deaths) + geom_col(aes(x=Monthly,y=new_deaths)) +
labs(title="Monthly new_deaths") +
scale_alpha_date()
